Advanced Search API with RAG capabilities - Developed by SKT AI LABS, India
Project description
🔍 SKT Search API
Advanced AI-Powered Search with RAG Capabilities
🚀 What is SKT Search?
SKT Search is a comprehensive, open-source search infrastructure that provides intelligent data retrieval and synthesis. It crawls the web, extracts high-quality information from diverse sources, and utilizes advanced language models to generate grounded, cited answers.
Optimized for efficiency. No expensive infrastructure required. Ready for cloud deployment.
✨ Features
- 🔍 Multi-Source Aggregation: Real-time results from multiple global search indices.
- 🕷️ Deep Web Extraction: Intelligent scraping of technical documentation and community forums.
- 🤖 Neural Synthesis: Integration with state-of-the-art open-source language models.
- 📚 RAG Engine: Retrieval Augmented Generation with precise source attribution.
- 💡 Cognitive Follow-ups: Context-aware related queries and deep-dive analysis.
- 🔑 Key Management: Full-featured API key issuance with granular rate limiting.
- 📊 Enterprise Dashboard: Administrative control for monitoring usage and managing tiers.
📦 Installation
pip install skt-search
🏗️ Architecture
- User Query: Input received via API or CLI.
- Search Layer: Multi-Engine Aggregator fetches raw data.
- Scraper: Document Parsing & Content Extraction.
- RAG Engine: Contextual Grounding & Source Citation.
- Neural Engine: LLM Inference via NRS System.
🛡️ Robustness & Scalability
- Identity Rotation: Automated agent switching to prevent request blocks.
- Adaptive Delays: Intelligent throttling for human-like interaction.
- Failover Logic: Automatic engine switching upon source unavailability.
📞 Support & Identity
- Organization: SKT AI LABS
- Project Goal: Sovereign AI Intelligence
- Official Site: https://huggingface.co/SKT-AI-LABS
📄 License
MIT License - SKT AI LABS
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file skt_search-1.0.2.tar.gz.
File metadata
- Download URL: skt_search-1.0.2.tar.gz
- Upload date:
- Size: 44.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f0ed5da86261f75e4a42cb3484e997e43c1b1ac70893bcc9d94b94256fde767a
|
|
| MD5 |
1c7c34111d5c62d96496e021e54da5d8
|
|
| BLAKE2b-256 |
bfe43b6ed06b761ff48a07b24d7dd0aa4df2e2d6c356b58c6b6281ecdc2732db
|
File details
Details for the file skt_search-1.0.2-py3-none-any.whl.
File metadata
- Download URL: skt_search-1.0.2-py3-none-any.whl
- Upload date:
- Size: 56.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bcfffce5d87cc73ac01c30f1a5abe3ff44f7157c68285526faf44f5dd4cc4f0e
|
|
| MD5 |
64aa2a821b0012d7a832ba91eefc2423
|
|
| BLAKE2b-256 |
113eaa8763699dca139f8629d9454074cb8df0fe8f4737136bc3a0f007433322
|